Weekly Exercises #3

library(tidyverse)     # for graphing and data cleaning
library(googlesheets4) # for reading googlesheet data
library(lubridate)     # for date manipulation
library(ggthemes)      # for even more plotting themes
library(geofacet)      # for special faceting with US map layout
gs4_deauth()           # To not have to authorize each time you knit.
theme_set(theme_minimal())       # My favorite ggplot() theme :)

#Lisa's garden data
garden_harvest <- read_sheet("https://docs.google.com/spreadsheets/d/1DekSazCzKqPS2jnGhKue7tLxRU3GVL1oxi-4bEM5IWw/edit?usp=sharing") %>% 
  mutate(date = ymd(date))

# Seeds/plants (and other garden supply) costs
supply_costs <- read_sheet("https://docs.google.com/spreadsheets/d/1dPVHwZgR9BxpigbHLnA0U99TtVHHQtUzNB9UR0wvb7o/edit?usp=sharing",
  col_types = "ccccnn")

# Planting dates and locations
plant_date_loc <- read_sheet("https://docs.google.com/spreadsheets/d/11YH0NtXQTncQbUse5wOsTtLSKAiNogjUA21jnX5Pnl4/edit?usp=sharing",
  col_types = "cccnDlc")%>% 
  mutate(date = ymd(date))

# Tidy Tuesday data
kids <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-09-15/kids.csv')

Warm-up exercises with garden data

These exercises will reiterate what you learned in the “Expanding the data wrangling toolkit” tutorial. If you haven’t gone through the tutorial yet, you should do that first.

1. Summarize the garden_harvest data to find the total harvest weight in pounds for each vegetable and day of week. Display the results so that the vegetables are rows but the days of the week are columns.

garden_harvest %>%
  mutate(week_day = wday(date, label = TRUE)) %>%
  group_by(week_day,vegetable) %>%
  mutate(wt_lbs = weight*0.00220462) %>%
  summarize(daily_wt_lbs = sum(wt_lbs)) %>%
  pivot_wider(id_cols = vegetable,
              names_from = week_day,
              values_from = daily_wt_lbs,
              values_fill = 0)

2. Summarize the garden_harvest data to find the total harvest in pound for each vegetable variety and then try adding the plot variable from the plant_date_loc table. This will not turn out perfectly. What is the problem? How might you fix it?

garden_summary <- garden_harvest %>%
  group_by(vegetable, variety, date) %>%
  mutate(wt_lbs = weight*0.00220462) %>%
  summarize(daily_wt_lbs = sum(wt_lbs))
  
  garden_summary %>%
  left_join(plant_date_loc,
            by = c("vegetable", "variety"))

As shown above, there is a replication of certain vegetables and varieties. For example, in row 17 and 18, the beans(Bush Bush Slender variety) harvested on 2020-07-06 are reported as harvested in both plot M and D. However, in reality these vegetables and variaties have not been harvest twice. When Lisa collected her data, she didn’t report the plot where she harvest from. Therefore, there is a replication of certain vegetables and varieties reported while that isn’t accurate. This could be fixed if Lisa would report the plot in which each vegetable and variety is harvested.

3. I would like to understand how much money I “saved” by gardening, for each vegetable type. Describe how I could use the garden_harvest and supply_cost datasets, along with data from somewhere like this to answer this question. You can answer this in words, referencing various join functions. You don’t need R code but could provide some if it’s helpful.

With the information provided on the Whole Foods Market website, we will be able to create a new dataset that shows the price of each vegetable, we will call this data set Whole_Foods. This will allow us to then join the Whole_Foods dataset with the supply_costs dataset, in order to show the vegetable and price. The Whole Foods Market website only shows prices for its vegetables without tax, I would therefore only use the variable price in the supply_costs dataset which does not account for tax to create a fair comparison.

supply_costs %>% left_join(Whole_Foods, by = c(“vegetable”)

4. Subset the data to tomatoes. Reorder the tomato varieties from smallest to largest first harvest date. Create a barplot of total harvest in pounds for each variety, in the new order.

garden_harvest %>% 
  filter(vegetable == "tomatoes") %>%
  group_by(variety) %>% 
  summarize(first_harvest_date = min(date), total_harvest_lbs = sum(weight) * 0.00220462) %>%
  arrange(first_harvest_date) -> ordered_by_date 
ordered_by_date

ordered_by_date %>%
  ggplot(aes(y = fct_relevel(variety, "grape", "Big Beef", "Bonny Best", "Better Boy", "Cherokee Purple", "Amish Paste", "Mortgage Lifter", "Jet Star", "Old German", "Black Krim", "Brandywine", "volunteers"), x = total_harvest_lbs)) +
  geom_col(fill = "darkred") +
          labs(title = "Total Harvest Weight of Different Tomato Varieties (Ordered by First Harvest   Date)", 
          x = "Total Harvest Weight (lbs)", 
          y = "Variety")

5. In the garden_harvest data, create two new variables: one that makes the varieties lowercase and another that finds the length of the variety name. Arrange the data by vegetable and length of variety name (smallest to largest), with one row for each vegetable variety. HINT: use str_to_lower(), str_length(), and distinct().

garden_harvest %>%
  mutate(variety_lower = str_to_lower(variety)) %>%
  mutate(variety_length = str_length(variety)) %>%
  mutate(variety2 = fct_infreq(variety)) %>%
  distinct(vegetable, variety, .keep_all = TRUE) %>%
  arrange(vegetable, variety_length) 

6. In the garden_harvest data, find all distinct vegetable varieties that have “er” or “ar” in their name. HINT: str_detect() with an “or” statement (use the | for “or”) and distinct().

garden_harvest %>%
  mutate(has_r = str_detect(variety, "er") | str_detect(variety, "ar")) %>%
  distinct(variety, has_r)

Bicycle-Use Patterns

In this activity, you’ll examine some factors that may influence the use of bicycles in a bike-renting program. The data come from Washington, DC and cover the last quarter of 2014.

{300px}

{300px}

Two data tables are available:

• Trips contains records of individual rentals
• Stations gives the locations of the bike rental stations

Here is the code to read in the data. We do this a little differently than usualy, which is why it is included here rather than at the top of this file. To avoid repeatedly re-reading the files, start the data import chunk with {r cache = TRUE} rather than the usual {r}.

data_site <- 
  "https://www.macalester.edu/~dshuman1/data/112/2014-Q4-Trips-History-Data.rds" 
Trips <- readRDS(gzcon(url(data_site)))
Stations<-read_csv("http://www.macalester.edu/~dshuman1/data/112/DC-Stations.csv")

NOTE: The Trips data table is a random subset of 10,000 trips from the full quarterly data. Start with this small data table to develop your analysis commands. When you have this working well, you should access the full data set of more than 600,000 events by removing -Small from the name of the data_site.

Temporal patterns

It’s natural to expect that bikes are rented more at some times of day, some days of the week, some months of the year than others. The variable sdate gives the time (including the date) that the rental started. Make the following plots and interpret them:

7. A density plot, which is a smoothed out histogram, of the events versus sdate. Use geom_density().

Trips %>%
  ggplot(aes(x = sdate)) +
  geom_density() +
  labs(title = "Event Versus Date",
       x = "Date",
       y = "Density")

In the density plot above, we observe that the bikes are rented more often during October and November than in December and January. This can be explained by the transition from spring weather into winter weather.

8. A density plot of the events versus time of day. You can use mutate() with lubridate’s hour() and minute() functions to extract the hour of the day and minute within the hour from sdate. Hint: A minute is 1/60 of an hour, so create a variable where 3:30 is 3.5 and 3:45 is 3.75.

Trips %>%
  mutate(time_of_day = hour(sdate) + (minute(sdate)/60)) %>%
    ggplot(aes(x = time_of_day)) +
    geom_density() +
    labs(title = "Event Versus Time of Day",
       x = "Time of Day",
       y = "Density")

In the density plot above, we observe the time of the day that bikes are rented out. As shown, bikes are rented out more often during two specific time periods of the day: early morning between 7am and 8am and in the afternoon between 5pm and 6pm. This can be explained by the fact that people use bikes during this time period to go to work in the morning and to go home in the afternoon. This is at the same time as the typical rush hour in public transportation.

9. A bar graph of the events versus day of the week. Put day on the y-axis.

Trips %>%
  mutate(days_of_week = wday(sdate, label = TRUE)) %>%
  ggplot(aes(y = days_of_week)) +
  geom_bar() +
  labs(title = "Event Versus Day of the Week",
       x = "Count",
       y = "Day of the Week")

As shown in the bar graph above, bikes are rented out more during the weekdays than during the weekends. This could be explained by the fact that individuals ren out these bikes to go from point A to point B during the workweek while they are off on the weekends and therefore don’t need to rent out a bike.

10. Facet your graph from exercise 8. by day of the week. Is there a pattern?

Trips %>%
  mutate(time_of_day = hour(sdate) + (minute(sdate)/60)) %>%
  mutate(days_of_week = wday(sdate, label = TRUE)) %>%
    ggplot(aes(x = time_of_day)) +
    geom_density() +
    facet_wrap(~days_of_week) +
    labs(title = "Event Versus Time and Day of the Week",
       x = "Time of Day",
       y = "Density")

There is a clear pattern during the weekdays as well as during the weekends. During the weekdays, there are peaks in the bike rentals during the early morning period before regular work hours start and in the afternoon after regular work hours have ended. Furthermore, both Saturday and Sunday have extremely similar patterns as most people use these bikes during the day (peak at 3pm) instead of during the early morning and/or late afternoon.

The variable client describes whether the renter is a regular user (level Registered) or has not joined the bike-rental organization (Causal). The next set of exercises investigate whether these two different categories of users show different rental behavior and how client interacts with the patterns you found in the previous exercises. Repeat the graphic from Exercise @ref(exr:exr-temp) (d) with the following changes:

11. Change the graph from exercise 10 to set the fill aesthetic for geom_density() to the client variable. You should also set alpha = .5 for transparency and color=NA to suppress the outline of the density function.

Trips %>%
  mutate(time_of_day = hour(sdate) + (minute(sdate)/60)) %>%
  mutate(days_of_week = wday(sdate, label = TRUE)) %>%
    ggplot(aes(x = time_of_day, fill=client)) +
    geom_density(color="NA", alpha = 0.5) +
    facet_wrap(~days_of_week) +
    labs(title = "Event Versus Time and Day of the Week",
       x = "Time of Day",
       y = "Density")

12. Change the previous graph by adding the argument position = position_stack() to geom_density(). In your opinion, is this better or worse in terms of telling a story? What are the advantages/disadvantages of each?

Trips %>%
  mutate(time_of_day = hour(sdate) + (minute(sdate)/60)) %>%
  mutate(days_of_week = wday(sdate, label = TRUE)) %>%
    ggplot(aes(x = time_of_day, fill=client)) +
    geom_density(color="NA", alpha = 0.5, position = position_stack()) +
    facet_wrap(~days_of_week) +
    labs(title = "Event Versus Time and Day of the Week",
       x = "Time of Day",
       y = "Density")

I believe that geom_density() is better visualization than the geom_density(position = position_stack()) because from the graphs with position = position_stack()) we are unable to determine when each client type are more likely to rent out the bikes independently from each other.

First plot, we are able to compare the distributions to each other. How did the times they ride differ. Second plot, we are able to show what proportion of the rides does each category represent. Saturday early morning, we are able to tell from the second plot that it’s mainly registered riders, while we are unable to tell this from the first plot.

13. Add a new variable to the dataset called weekend which will be “weekend” if the day is Saturday or Sunday and “weekday” otherwise (HINT: use the ifelse() function and the wday() function from lubridate). Then, update the graph from the previous problem by faceting on the new weekend variable.

Trips %>%
  mutate(time_of_day = hour(sdate) + (minute(sdate)/60)) %>%
  mutate(days_of_week = wday(sdate, label = TRUE)) %>%
  mutate(weekend = ifelse(days_of_week %in% c("Sat", "Sun"), "Weekend", "Weekday")) %>%
    ggplot(aes(x = time_of_day, fill=client), color="NA", alpha = 0.5) +
    geom_density(position = position_stack()) +
    facet_wrap(~weekend) +
    labs(title = "Different Client Usage",
       x = "Time of Day",
       y = "Density")

14. Change the graph from the previous problem to facet on client and fill with weekday. What information does this graph tell you that the previous didn’t? Is one graph better than the other?

Trips %>%
  mutate(time_of_day = hour(sdate) + (minute(sdate)/60)) %>%
  mutate(days_of_week = wday(sdate, label = TRUE)) %>%
  mutate(weekend = ifelse(days_of_week %in% c("Sat", "Sun"), "Weekend", "Weekday")) %>%
    ggplot(aes(x = time_of_day, fill=days_of_week), color="NA", alpha = 0.5) +
    geom_density(position = position_stack()) +
    facet_wrap(~client) +
    labs(title = "Different Client Usage",
       x = "Time of The Day",
       y = "Density")

The graph above tells us more specific information about each day of the week which allows us to determine which day shave the most casual and registered users respectively. I do not believe that one graph is better than the other, they both give different information that is useful to answer different questions.

Spatial patterns

15. Use the latitude and longitude variables in Stations to make a visualization of the total number of departures from each station in the Trips data. Use either color or size to show the variation in number of departures. We will improve this plot next week when we learn about maps!

Stations %>%
  left_join(Trips,
  by = c("name" = "sstation")) %>%
    group_by(name) %>% 
    mutate(total_departures = n()) %>% 
      ggplot(aes(x = long, y = lat, color = total_departures)) +
      geom_jitter() +
        labs(title = "Total Departures from Each Rental Location", 
        x = "Longitude", 
        y ="Latitude")

16. Only 14.4% of the trips in our data are carried out by casual users. Create a plot that shows which area(s) have stations with a much higher percentage of departures by casual users. What patterns do you notice? (Again, we’ll improve this next week when we learn about maps).

Stations %>%
  left_join(Trips,
            by = c("name" = "sstation")) %>%
  group_by(name, long, lat) %>% 
  summarize(percent_casual= mean(client == "Casual")) %>% 
  ggplot(aes(x = long, y = lat, color = percent_casual)) +
  geom_point() +
  labs(title = "Total Departures from Each Rental Location", 
       x = "Longitude", 
       y ="Latitute")

There are many stations along the 38.9 latitude, which could be explained by the fact that this is a downtown area in the middle of a city, with metro and train stations located in this area. Furthermore, there seems to be a diagonal street from left top to bottom right with the amount of stations that fit into that pattern. Lastly, there seems to be a high percentage of casual riders at certain stations along the -77.05 longitude. Once again, this is possibly the center of the downtown area where casual riders rent out their bikes.

Spatiotemporal patterns

17. Make a table with the ten station-date combinations (e.g., 14th & V St., 2014-10-14) with the highest number of departures, sorted from most departures to fewest. Save this to a new dataset and print out the dataset. Hint: as_date(sdate) converts sdate from date-time format to date format.

Top_Trips <- Trips %>%
  mutate(trip_date = as_date(sdate)) %>%
  group_by(sstation, trip_date) %>%
  count() %>%
  arrange(desc(n)) %>%
  head(10)
Top_Trips

18. Use a join operation to make a table with only those trips whose departures match those top ten station-date combinations from the previous part.

Trips%>%
  mutate(trip_date = as_date(sdate)) %>%
  inner_join(Top_Trips, 
            by = c("sstation", "trip_date"))

19. Build on the code from the previous problem (ie. copy that code below and then %>% into the next step.) and group the trips by client type and day of the week (use the name, not the number). Find the proportion of trips by day within each client type (ie. the proportions for all 7 days within each client type add up to 1). Display your results so day of week is a column and there is a column for each client type. Interpret your results.

Trips %>%
  mutate(trip_date = as_date(sdate)) %>%
  inner_join(Top_Trips,
             by = c("sstation", "trip_date")) %>%
  mutate(days_of_week = wday(sdate, label = TRUE)) %>%
  group_by(client, days_of_week) %>%
  summarize(number_riders = n()) %>%
  mutate(total_prop = number_riders/sum(number_riders)) %>%
  pivot_wider(id_cols = days_of_week,
              names_from = client,
              values_from = total_prop)

At the ten station-date combinations with the highest number of departures, the
Casual = 36% on Sunday, 56% on Saturday

Make a table with the ten station-date combinations (e.g., 14th & V St., 2014-10-14) with the highest number of departures, sorted from most departures to fewest.

DID YOU REMEMBER TO GO BACK AND CHANGE THIS SET OF EXERCISES TO THE LARGER DATASET? IF NOT, DO THAT NOW.

GitHub link

20. Below, provide a link to your GitHub page with this set of Weekly Exercises. Specifically, if the name of the file is 03_exercises.Rmd, provide a link to the 03_exercises.md file, which is the one that will be most readable on GitHub.

Challenge problem!

This problem uses the data from the Tidy Tuesday competition this week, kids. If you need to refresh your memory on the data, read about it here.

21. In this exercise, you are going to try to replicate the graph below, created by Georgios Karamanis. I’m sure you can find the exact code on GitHub somewhere, but DON’T DO THAT! You will only be graded for putting an effort into this problem. So, give it a try and see how far you can get without doing too much googling. HINT: use facet_geo(). The graphic won’t load below since it came from a location on my computer. So, you’ll have to reference the original html on the moodle page to see it.

kids %>%
  filter(variable == "lib") %>%
  filter(year == 1997 | year == 2016) %>%
  ggplot(aes(x = year, y = inf_adj_perchild)) +
  geom_line() +
  scale_color_identity() +
  facet_geo(vars(state)) +
  labs(title = "Change in public spending on libraries from 1997 to 2016",
       subtitle = "Dollars spent per child, adjusted for inflation")

kids %>%
  filter(variable %in% "lib") %>%
  ggplot(aes(x = year, y = inf_adj_perchild)) +
  geom_line(color = "white", size =2) +
  theme(legend.position = "") +
  theme_void() +
  theme(plot.background = element_rect(fill = "lightsteelblue4")) +
  facet_geo(vars(state), grid = "us_state_grid3", label = "name") +
  labs(title="Change in public spending on libraries",
       subtitle = "Dollars spent per child, adjusted for inflation")+
  theme(plot.title = element_text(hjust = 0.5, size =20, face = "bold"),
        plot.subtitle = element_text(hjust = 0.5, size = 15))

DID YOU REMEMBER TO UNCOMMENT THE OPTIONS AT THE TOP?